© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28689
    Prev
    Next
    INDEX
    Explanations

    ending with fty or EM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¢
    -0.07
    赶
    -0.06
    ium
    -0.06
    æķ¢
    -0.06
    è¿ĩå¾Ĺ
    -0.06
    care
    -0.06
    ament
    -0.05
    éŃĤ
    -0.05
    äºĨ
    -0.05
    -E
    -0.05
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩéĥ½
    0.10
    çļĦè¯Ħä»·æĺ¯
    0.09
    以任ä½ķ
    0.09
    çļĦä½ľçĶ¨æĺ¯
    0.09
    ä½ľçĶ¨æĺ¯
    0.08
    roman
    0.08
     **>>
    0.08
    otka
    0.08
    çļĦ人ä¼ļ
    0.08
    æī°
    0.08
    Activations Density 0.018%

    No Known Activations